Weekly Exercises #5

library(tidyverse)     # for data cleaning and plotting

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.0.5     ✓ dplyr   1.0.3
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(gardenR)       # for Lisa's garden data
library(lubridate)     # for date manipulation

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(openintro)     # for the abbr2state() function

## Loading required package: airports

## Loading required package: cherryblossom

## Loading required package: usdata

library(palmerpenguins)# for Palmer penguin data
library(maps)          # for map data

## 
## Attaching package: 'maps'

## The following object is masked from 'package:purrr':
## 
##     map

library(ggmap)         # for mapping points on maps

## Google's Terms of Service: https://cloud.google.com/maps-platform/terms/.

## Please cite ggmap if you use it! See citation("ggmap") for details.

library(gplots)        # for col2hex() function

## 
## Attaching package: 'gplots'

## The following object is masked from 'package:stats':
## 
##     lowess

library(RColorBrewer)  # for color palettes
library(sf)            # for working with spatial data

## Linking to GEOS 3.8.1, GDAL 3.1.4, PROJ 6.3.1

library(leaflet)       # for highly customizable mapping
library(ggthemes)      # for more themes (including theme_map())
library(plotly)        # for the ggplotly() - basic interactivity

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggmap':
## 
##     wind

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(gganimate)     # for adding animation layers to ggplots
library(transformr)    # for "tweening" (gganimate)

## 
## Attaching package: 'transformr'

## The following object is masked from 'package:sf':
## 
##     st_normalize

library(gifski)        # need the library for creating gifs but don't need to load each time
library(shiny)         # for creating interactive apps
library(ggimage)

## 
## Attaching package: 'ggimage'

## The following object is masked from 'package:ggmap':
## 
##     theme_nothing

# SNCF Train data
small_trains <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-02-26/small_trains.csv") 

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   year = col_double(),
##   month = col_double(),
##   service = col_character(),
##   departure_station = col_character(),
##   arrival_station = col_character(),
##   journey_time_avg = col_double(),
##   total_num_trips = col_double(),
##   avg_delay_all_departing = col_double(),
##   avg_delay_all_arriving = col_double(),
##   num_late_at_departure = col_double(),
##   num_arriving_late = col_double(),
##   delay_cause = col_character(),
##   delayed_number = col_double()
## )

# Lisa's garden data
data("garden_harvest")

# Lisa's Mallorca cycling data
mallorca_bike_day7 <- read_csv("https://www.dropbox.com/s/zc6jan4ltmjtvy0/mallorca_bike_day7.csv?dl=1") %>% 
  select(1:4, speed)

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   lon = col_double(),
##   lat = col_double(),
##   ele = col_double(),
##   time = col_datetime(format = ""),
##   extensions = col_double(),
##   ele.num = col_double(),
##   date = col_date(format = ""),
##   hrminsec = col_datetime(format = ""),
##   time_hr = col_double(),
##   dist_km = col_double(),
##   speed = col_double()
## )

# Heather Lendway's Ironman 70.3 Pan Am championships Panama data
panama_swim <- read_csv("https://raw.githubusercontent.com/llendway/gps-data/master/data/panama_swim_20160131.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   lon = col_double(),
##   lat = col_double(),
##   time = col_datetime(format = ""),
##   extensions = col_double(),
##   ele = col_logical(),
##   event = col_character(),
##   date = col_date(format = ""),
##   hrminsec = col_datetime(format = "")
## )

panama_bike <- read_csv("https://raw.githubusercontent.com/llendway/gps-data/master/data/panama_bike_20160131.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   lon = col_double(),
##   lat = col_double(),
##   ele = col_double(),
##   time = col_datetime(format = ""),
##   extensions = col_double(),
##   event = col_character(),
##   date = col_date(format = ""),
##   hrminsec = col_datetime(format = "")
## )

panama_run <- read_csv("https://raw.githubusercontent.com/llendway/gps-data/master/data/panama_run_20160131.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   lon = col_double(),
##   lat = col_double(),
##   ele = col_double(),
##   time = col_datetime(format = ""),
##   extensions = col_double(),
##   event = col_character(),
##   date = col_date(format = ""),
##   hrminsec = col_datetime(format = "")
## )

#COVID-19 data from the New York Times
covid19 <- read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   date = col_date(format = ""),
##   state = col_character(),
##   fips = col_character(),
##   cases = col_double(),
##   deaths = col_double()
## )

Instructions

• For ALL graphs, you should include appropriate labels.

• NEW!! With animated graphs, add eval=FALSE to the code chunk that creates the animation and saves it using anim_save(). Add another code chunk to reread the gif back into the file. See the tutorial for help.

Warm-up exercises from tutorial

1. Choose 2 graphs you have created for ANY assignment in this class and add interactivity using the ggplotly() function.

covid_cumcase <-covid19 %>% 
  filter(state %in% c("Minnesota", "Wisconsin", "Iowa", "North Dakota", "South Dakota")) %>% 
  ggplot(aes(x = date, y = cases, color = state)) +
  geom_line() +
  labs(x = "",
       y = "",
       color = "",
       title = "Cumulative COVID-19 cases") +
  theme(legend.position = "bottom") +
  scale_y_continuous(labels = scales::comma) + 
  scale_x_date(date_breaks = "1 month",
               date_labels = "%b",
               date_minor_breaks = "1 week")

ggplotly(covid_cumcase)

lettuce_variety <- garden_harvest %>% 
  filter(vegetable == "lettuce") %>% 
  ggplot(aes(y = fct_rev(fct_infreq(variety)))) +
  geom_bar() +
  labs(title = "Number of times lettuce \n varieties were harvested",
       x = "",
       y = "")

ggplotly(lettuce_variety)

2. Use animation to tell an interesting story with the small_trains dataset that contains data from the SNCF (National Society of French Railways). These are Tidy Tuesday data! Read more about it here.

trains_journey <- small_trains %>% 
  ggplot(aes(x = journey_time_avg, y = num_arriving_late)) +
  geom_point(alpha = .5) +
  theme(axis.text.y = element_blank(),
        plot.title = element_text(face = "bold", hjust = .5),
        axis.text = element_text(color = "black", face = "italic")) +
  labs(title = "Train journey average by the total number of trains arriving late over the years", 
       x = "Journey time average",
       y = "Number of trains arriving late") +
  facet_wrap(vars(year))

trains_journey +
  transition_time(journey_time_avg)

anim_save("journeys.gif")

knitr::include_graphics("journeys.gif")

Garden data

3. In this exercise, you will create a stacked area plot that reveals itself over time (see the geom_area() examples here). You will look at cumulative harvest of tomato varieties over time. You should do the following:

• From the garden_harvest data, filter the data to the tomatoes and find the daily harvest in pounds for each variety.
  
• Then, for each variety, find the cumulative harvest in pounds.
  
• Add animation to reveal the plot over date.
• Use the data you just made to create a static cumulative harvest area plot, with the areas filled with different colors for each vegetable and arranged (HINT: fct_reorder()) from most to least harvested (most on the bottom).

tomatoes_cum <- garden_harvest %>% 
  filter(vegetable == "tomatoes") %>% 
  group_by(date, variety) %>% 
  summarize(daily_harvest_lbs = sum(weight)*0.00220462) %>% 
  ungroup() %>% 
  complete(variety, date, fill = list(daily_harvest_lbs = 0)) %>% 
  group_by(variety) %>% 
  mutate(cum_wt_lbs = cumsum(daily_harvest_lbs)) %>% 
  ggplot(aes(x = date, y = cum_wt_lbs, fill = fct_reorder(variety, cum_wt_lbs, max))) + 
  geom_area() +
  labs(title = "Cumulative Tomato Harvest by variety (lbs)",
       fill = "Varieties",
       x = "", 
       y = "") +
  theme(plot.title = element_text(face = "bold", hjust = .5)) 

tomatoes_cum +
  transition_reveal(date)

anim_save("tomato_varieties.gif")

knitr::include_graphics("tomato_varieties.gif")

Maps, animation, and movement!

4. Map my mallorca_bike_day7 bike ride using animation! Requirements:

• Plot on a map using ggmap.
• Show path up until the current point.
  
• Color the path according to elevation.
  
• Show the time in the subtitle.
• Show “current” location with a red point.
• CHALLENGE: use the ggimage package and geom_image to add a bike image instead of a red point. You can use this image. See here for an example.
• Add something of your own! And comment on if you prefer this to the static map and why or why not.

I prefer this animated map because it is more dynamic and gives more of an idea of how your bike ride went.

bike_image_link <- "https://raw.githubusercontent.com/llendway/animation_and_interactivity/master/bike.png"

mallorca_map <- get_stamenmap(
    bbox = c(left = 2.28, bottom = 39.41, right = 3.03, top = 39.8), 
    maptype = "terrain",
    zoom = 11)

bikeride <- ggmap(mallorca_map) +
  geom_path(data = mallorca_bike_day7, 
             aes(x = lon, y = lat, color = ele, size = speed)) +
  scale_color_viridis_c(option = "magma") +
  geom_image(data = mallorca_bike_day7 %>% 
            mutate(picture = bike_image_link),
             aes(x = lon, y = lat, image = picture),
             size = 0.07) +
  labs(title = "Lisa's Mallorca bike ride",
       subtitle = "Time : {frame_along}",
       x = "", 
       y = "") +
  theme_map() +
  theme(plot.title = element_text(face = "bold", hjust = .5, size = 20),
        plot.subtitle = element_text(face = "bold", hjust = .5, size = 15))

bikeride +
  transition_reveal(time)

anim_save("lisa_ride.gif")

knitr::include_graphics("lisa_ride.gif")

5. In this exercise, you get to meet my sister, Heather! She is a proud Mac grad, currently works as a Data Scientist at 3M where she uses R everyday, and for a few years (while still holding a full-time job) she was a pro triathlete. You are going to map one of her races. The data from each discipline of the Ironman 70.3 Pan Am championships, Panama is in a separate file - panama_swim, panama_bike, and panama_run. Create a similar map to the one you created with my cycling data. You will need to make some small changes:
6. combine the files (HINT: bind_rows(),
7. make the leading dot a different color depending on the event (for an extra challenge, make it a different image using `geom_image()!)

panama_all <- bind_rows(panama_swim, panama_bike, panama_run)

Panama <- get_stamenmap(
  bbox = c(left = -79.8420, bottom = 8.7394, right = -79.2034, top = 9.1159),
  maptype = "terrain",
  zoom = 10)

heather_ironman <- ggmap(Panama) +
  geom_path(data = panama_all,
            aes(x = lon, y = lat),
            size = 1) +
  geom_point(data = panama_all,
             aes(x = lon, y = lat, color = event),
             size = 3) +
   labs(title = "Heather's Panama triatholon",
       x = "", 
       y = "",
       color = "Event") +
  theme(plot.title = element_text(face = "bold", hjust = .5)) +
  theme_map() 

heather_ironman +
  transition_reveal(hrminsec)

anim_save("ironman.gif")

knitr::include_graphics("ironman.gif")

COVID-19 data

6. In this exercise, you are going to replicate many of the features in this visualization by Aitish Bhatia but include all US states. YES Requirements:

• Create a new variable that computes the number of new cases in the past week (HINT: use the lag() function you’ve used in a previous set of exercises). Replace missing values with 0’s using replace_na().
  
• Filter the data to omit rows where the cumulative case counts are less than 20.
  
• Create a static plot with cumulative cases on the x-axis and new cases in the past 7 days on the y-axis. Connect the points for each state over time. HINTS: use geom_path() and add a group aesthetic. Put the x and y axis on the log scale and make the tick labels look nice - scales::comma is one option. This plot will look pretty ugly as is.
• Animate the plot to reveal the pattern by date. Display the date as the subtitle. Add a leading point to each state’s line (geom_point()) and add the state name as a label (geom_text() - you should look at the check_overlap argument).
  
• Use the animate() function to have 200 frames in your animation and make it 30 seconds long.
• Comment on what you observe.

It is quite hard to differentiate each line from one another but overall, the growth of covid is exponential with new cases everyday, the cumulative cases keep rising. By the end of the gif it seems California and Florida and Texas have the most cases so far with slight dips in the count but is still overall quite a lot and still growing.

cum_covid19 <- covid19 %>% 
  group_by(state) %>% 
  mutate(seven_lag = lag(cases, 7, order_by = date)) %>% 
  replace_na(list(seven_lag = 0)) %>% 
  ungroup() %>% 
  mutate(new_weekly_cases = cases - seven_lag) %>% 
  filter(cases >= 20) %>% 
  
  ggplot(aes( x = cases, y = new_weekly_cases, group = state)) +
  geom_point(color = "red") +
  geom_path(color = "blue") +
  geom_text(aes(label = state),
            check_overlap = TRUE) +
  scale_y_log10(label = scales::comma) +
  scale_x_log10(label = scales::comma) +
  labs(title = "New Covid Cases vs Cumulative Covid Cases",
       x = "", 
       y = "") +
  theme(plot.title = element_text(face = "bold", hjust = .5)) +
    transition_reveal(date) 
  
animate(cum_covid19, nframes = 200, duration = 30)

anim_save("covid19_US.gif")

knitr::include_graphics("covid19_US.gif")

7. In this exercise you will animate a map of the US, showing how cumulative COVID-19 cases per 10,000 residents has changed over time. This is similar to exercises 11 & 12 from the previous exercises, with the added animation! So, in the end, you should have something like the static map you made there, but animated over all the days. The code below gives the population estimates for each state and loads the states_map data. Here is a list of details you should include in the plot:

• Put date in the subtitle.
  
• Because there are so many dates, you are going to only do the animation for all Fridays. So, use wday() to create a day of week variable and filter to all the Fridays.
• Use the animate() function to make the animation 200 frames instead of the default 100 and to pause for 10 frames on the end frame.
  
• Use group = date in aes().
  
• Comment on what you see.

census_pop_est_2018 <- read_csv("https://www.dropbox.com/s/6txwv3b4ng7pepe/us_census_2018_state_pop_est.csv?dl=1") %>% 
  separate(state, into = c("dot","state"), extra = "merge") %>% 
  select(-dot) %>% 
  mutate(state = str_to_lower(state))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   state = col_character(),
##   est_pop_2018 = col_double()
## )

states_map <- map_data("state")

covidanim <- covid19 %>% 
  mutate(state_name = str_to_lower(state)) %>% 
  group_by(state) %>% 
  mutate(weekday = wday(date, label = TRUE)) %>% 
  filter(weekday == "Fri") %>% 
  left_join(census_pop_est_2018, by = c("state_name" = "state")) %>% 
  mutate(cases_per_10000 = (cumsum(cases)/est_pop_2018)*10000) %>% 
  ggplot() +
  geom_map(map = states_map,
           aes(map_id = state_name,
               fill = cases_per_10000,
               group = date)) +
  scale_fill_viridis_c(option = "inferno") +
  expand_limits(x = states_map$long, y = states_map$lat) +
  labs(title = "New Covid Cases per 10,000 habitants",
       subtitle = "Date : {frame_along}",
       x = "",
       y = "") +
  theme(plot.title = element_text(face = "bold", hjust = .5, size = 17),
        plot.subtitle = element_text(face = "bold", hjust = .5, size = 10)) +
  theme_map() +
  transition_reveal(date) 

animate(covidanim, nframes = 200, end_pause = 10)

anim_save("covid_USmap.gif")

GitHub link

9. Below, provide a link to your GitHub page with this set of Weekly Exercises. Specifically, if the name of the file is 05_exercises.Rmd, provide a link to the 05_exercises.md file, which is the one that will be most readable on GitHub. If that file isn’t very readable, then provide a link to your main GitHub page.

DID YOU REMEMBER TO UNCOMMENT THE OPTIONS AT THE TOP?